Logo do repositório

ESS - NEU - Artigos

URI permanente para esta coleção:

http://hdl.handle.net/10400.22/1077

Navegar

Percorrer ESS - NEU - Artigos por assunto "Artificial intelligence"

A mostrar 1 - 2 de 2
  • Before the spike: Human oversight of artificial intelligence in EEG interpretation requires reasoning beyond recognition
    Publication . Borges, Daniel Filipe; Leal, Alberto; Borges, Daniel Filipe
    Artificial intelligence (AI) is transforming EEGinterpretation faster than training is adapting to definewhat competent interpretation now requires. Errors arisebefore the first abnormal waveform appears, in whattrainees encounter, how they examine evidence, and howreadily a signal becomes a diagnostic label. That path isalready shortening: a deep neural network has achievedexpert- level detection of interictal epileptiform dischargesin selected settings.1 As automated recognition growsmore capable, human verification becomes more, notless, consequential. Protecting patients requires readers toreconstruct, defend, and revise the reasoning from signalto conclusion. What makes verification credible? Presenceis insufficient unless readers can explain why an output isplausible and recognize when it is not.
    2026-08-29Carta ao editor Acesso embargado Ver mais
  • Comparative evaluation of artificial intelligence chatbots in answering electroencephalography-related questions
    Publication . Proença, Soraia; Soares, Joana Isabel; Parra, Joana; Maia, Gisela; Leite, Juliana; Beniczky, Sándor; Jesus-Ribeiro, Joana; Henrique Maia, Gisela Maria
    As large language models (LLMs) become more accessible, they may be used to explain challenging EEG concepts to nonspecialists. This study aimed to compare the accuracy, completeness, and readability of EEG-related responses from three LLM-based chatbots and to assess inter-rateragreement. One hundred questions, covering 10 EEG categories, were entered into ChatGPT, Copilot, and Gemini. Six raters from the clinical neurophysiology field (two physicians, two teachers, and two technicians) evaluated the responses. Accuracy was rated on a 6-point scale, completeness on a 3-point scale, and readability was assessed using the Automated Readability Index (ARI). We used a repeated-measures ANOVA for group differences in accuracy and readability, the intraclass correlation coefficient (ICC) for inter-raterreliability, and a two way ANOVA, with chatbot and raters as factors, for completeness. Total accuracy was significantly higher for ChatGPT (mean ± SD 4.54 ± .05) compared with Copilot (mean ± SD 4.11 ± .08) and Gemini (mean ± SD 4.16 ± .13) (p < .001). ChatGPT's lowest performance was in normal variants and patterns of uncertain significance (mean ± SD 3.10 ± .14), while Copilot and Gemini performed lowest in ictal EEG patterns (mean ± SD 2.93 ± .11 and 3.37 ± .24, respectively). Although inter-rater agreement for accuracy was excellent among physicians (ICC = .969) and teachers (ICC = .926), it was poor for technicians in several EEG categories. ChatGPT achieved significantly higher completeness scores than Copilot (p < .001) and Gemini (p = .01). ChatGPT text (ARI − mean ± SD 17.41 ± 2.38) was less readable than Copilot (ARI −mean ± SD 11.14 ± 2.60) (p < .001) and Gemini (ARI − mean ± SD 14.16 ± 3.33). Chatbots achieved relatively high accuracy, but not without flaws, emphasizing that the information provided requires verification. ChatGPT outperformed the other chatbots in accuracy and completeness, though at the expense of readability. The lower inter-rater agreement among technicians may reflect a gap in standardized training or practical experience, potentially impacting the consistency of EEG-related content assessment.
    2025-12-05Artigo científico Acesso embargado Ver mais